Spatiotemporal Feature Learning
Spatiotemporal Feature Learning is a computational approach in computer vision that, as a subset of feature learning methods, specifically captures and models the joint spatial configuration and temporal dynamics of actions in video sequences to enable accurate action recognition.
1.6K
Publications
173.8K
Citations
4.9K
Authors
1.2K
Institutions
Publications per year
2017–2026
1.2K
Parents
1.6K
Learning Spatiotemporal Features with 3D Convolutional Networks
Du Tran, Lubomir Bourdev, Rob Fergus et al. · 2015 · 9.7K citations
Large-Scale Video Classification with Convolutional Neural Networks
Andrej Karpathy, George Toderici, Sanketh Shetty et al. · 2014 · 6.3K citations
SlowFast Networks for Video Recognition
Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik et al. · 2019 · 3.6K citations
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Du Tran, Heng Wang, Lorenzo Torresani et al. · 2018 · 3.5K citations
1–5 of 1.6K
4.9K
15
h-index
14
h-index
14
h-index
13
h-index
13
h-index
1–5 of 4.9K
1.2K

Chinese Academy of Sciences
Beijing, China
38 h-index
182 publications
19.4K citations
University of Chinese Academy of Sciences
Beijing, China
33 h-index
143 publications
13.8K citations

Beihang University
Beijing, China
25 h-index
96 publications
5K citations
Nanyang Technological University
Singapore, Singapore
24 h-index
55 publications
5.8K citations

Peking University
Beijing, China
24 h-index
90 publications
5.8K citations
Chinese University of Hong Kong
Hong Kong, Hong Kong
24 h-index
67 publications
28.7K citations
Tsinghua University
Beijing, China
24 h-index
100 publications
10.3K citations

Shanghai Jiao Tong University
Shanghai, China
22 h-index
93 publications
11.1K citations
1–8 of 1.2K
Repository · 150 publications · 11.6K citations
51
h-index
50 publications · 4.3K citations
36
h-index
54 publications · 3.3K citations
32
h-index
44 publications · 3K citations
31
h-index
54 publications · 2.3K citations
29
h-index
1–5